MultiQG-TI: Towards Question Generation from Multi-modal Sources
This addresses the need for question generation from multi-modal data, expanding beyond text-only methods, though it is incremental as it builds on existing components.
The paper tackles the problem of automatic question generation from multi-modal sources (images and texts) by proposing MultiQG-TI, which adapts a text-only generator to handle visual input, resulting in significant outperformance over ChatGPT on the ScienceQA dataset with hundred-times fewer parameters.
We study the new problem of automatic question generation (QG) from multi-modal sources containing images and texts, significantly expanding the scope of most of the existing work that focuses exclusively on QG from only textual sources. We propose a simple solution for our new problem, called MultiQG-TI, which enables a text-only question generator to process visual input in addition to textual input. Specifically, we leverage an image-to-text model and an optical character recognition model to obtain the textual description of the image and extract any texts in the image, respectively, and then feed them together with the input texts to the question generator. We only fine-tune the question generator while keeping the other components fixed. On the challenging ScienceQA dataset, we demonstrate that MultiQG-TI significantly outperforms ChatGPT with few-shot prompting, despite having hundred-times less trainable parameters. Additional analyses empirically confirm the necessity of both visual and textual signals for QG and show the impact of various modeling choices.